
import unittest
import user_code
import ast
import re   
import unittest
import pandas as pd
import importlib
import user_code

class TestTask(unittest.TestCase):
    def setUp(self):
        self.data = {
            "name": ["Alice", "Bob", "Charlie"],
            "ssn": ["123-45-6789", "987-65-4321", "555-66-7777"],
            "email": ["alice@example.com", "bob@example.com", "charlie@example.com"]
        }
        self.df = pd.DataFrame(self.data)

    def test_sensitive_columns_masked(self):
        importlib.reload(user_code)
        sensitive_columns = ["ssn", "email"]
        masked_df = user_code.mask_sensitive_data(self.df, sensitive_columns)
        mask = "***MASKED***"
        for col in sensitive_columns:
            if col in masked_df.columns:
                _dynamic_test(
                    self,
                    (masked_df[col] == mask).all(),
                    f"Column '{col}' is correctly masked with '{mask}'",
                    f"Column '{col}' is not correctly masked: {masked_df[col].tolist()}"
                )

    def test_non_sensitive_columns_unchanged(self):
        importlib.reload(user_code)
        sensitive_columns = ["ssn"]
        masked_df = user_code.mask_sensitive_data(self.df, sensitive_columns)
        _dynamic_test(
            self,
            masked_df["name"].equals(self.df["name"]),
            "Non-sensitive columns remain unchanged",
            f"Non-sensitive column 'name' was changed: {masked_df['name'].tolist()}"
        )

    def test_ignore_nonexistent_column(self):
        importlib.reload(user_code)
        sensitive_columns = ["ssn", "passport_number"]
        try:
            masked_df = user_code.mask_sensitive_data(self.df, sensitive_columns)
            _dynamic_test(
                self,
                True,
                "Function does not raise error for non-existent sensitive column",
                "Function raised error for non-existent sensitive column"
            )
        except Exception as e:
            _dynamic_test(
                self,
                False,
                "Function does not raise error for non-existent sensitive column",
                f"Function raised error: {e}"
            )

    def test_returns_copy(self):
        importlib.reload(user_code)
        sensitive_columns = ["ssn"]
        df_original = self.df.copy()
        masked_df = user_code.mask_sensitive_data(self.df, sensitive_columns)
        _dynamic_test(
            self,
            not masked_df.equals(self.df) or (masked_df is not self.df),
            "Returned DataFrame is a new object and does not modify the original",
            "Returned DataFrame is the same object as the original or modifies it in place"
        )
        # Ensure original is unchanged
        _dynamic_test(
            self,
            self.df.equals(df_original),
            "Original DataFrame remains unchanged",
            "Original DataFrame was modified"
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()


test_main.py

Learn how to write secure Python code by understanding common vulnerabilities, safe coding techniques, and practical security measures. This course covers essential security concepts, real-world scenarios, and hands-on tasks to help you protect your Python applications.

Explore the most common security pitfalls in Python, how vulnerabilities arise, and the foundational principles for writing secure code.

Master secure coding techniques to prevent vulnerabilities and ensure robust Python applications.

Learn how to handle, store, and process sensitive data securely in Python applications.

Challenge: Masking Sensitive Data in DataFrames

Ratkaisu

Awesome!

Challenge: Masking Sensitive Data in DataFrames

Ratkaisu